Fuses the information from the Fast pathway to the Slow pathway. Given the tensors from Slow pathway and Fast pathway, fuse information from

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Internal implementation of Pascal object detection metrics.

A scalar meter uses a deque to track a series of scaler values with a given window size. It supports calculating the median and average value

Measure the PSI-AVA train, val, and test stats.

Swish activation function: x * sigmoid(x).

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

A timer which computes the epoch time.

Multilayer perceptron.

Builds Non-local Neural Networks as a generic family of building blocks for capturing long-range dependencies. Non-local Network computes

Video to Patch Embedding. Args: patch_size (int): Patch token size. Default: (2,4,4). in_chans (int): Number of input video chan

Residual block.

Squeeze-and-Excitation (SE) block w/ Swish: AvgPool, FC, Swish, FC, Sigmoid.

Swin Transformer Block. Args: dim (int): Number of input channels. num_heads (int): Number of attention heads. window_si

A task meter uses a deque to track a series of scaler values with a given window size. It supports calculating the median and average values

Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. Args:

We adapt the AVA Dataset management in Slowfast to manage PSI-AVA database.

Basic transformation: Tx3x3, 1x3x3, where T is the size of temporal kernel.

Bottleneck transformation: Tx1x1, 1x3x3, 1x1x1, where T is the size of temporal kernel.

Box collection. BoxList represents a list of bounding boxes as numpy array, where each bounding box is represented as a row of 4 numbers, [y_mi

Naming conventions for BoxLists. Attributes: boxes: bounding box coordinates. classes: classes per bounding box. scores: scores per bou

Convenience wrapper for BoxList with masks. BoxMaskList extends the np_box_list.BoxList to contain masks as well. In particular, its constructor

Interface for object detection evalution classes. Example usage of the Evaluator: ------------------------------ evaluator = DetectionEvaluator

Naming conventions for storing the output of the detector. Attributes: source_id: source of the original image. key: unique key correspondi

GroupGather performs all gather on each of the local process/ GPU groups.

Names for the input tensors. Holds the standard data field names to use for identifying input tensors. This should be used by the decoder to iden

Multiscale Vision Transformers Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, Christoph Feichtenhofer

This class defines multigrid training schedule and update cfg accordingly.

A class to evaluate detections.

A class to evaluate detections using Open Images V2 metrics. Open Images V2 introduce group_of type of bounding boxes and this metric handles

A class to evaluate detections using PASCAL metrics.

A class to evaluate instance masks using PASCAL metrics.

PatchEmbed.

Patch Merging Layer Args: dim (int): Number of input channels. norm_layer (nn.Module, optional): Normalization layer. Default:

Evaluate detection result of a single image.

Crop the given PIL Image to random size and aspect ratio with random interpolation. A crop of random size (default: of 0.08 to 1.0) of the origina

ResNe(X)t 3D head. This layer performs a fully-connected projection during training, when the input size is 1x1x1. It performs a convolut

ResNe(X)t 3D stem module. Performs spatiotemporal Convolution, BN, and Relu following by a spatiotemporal pooling.

ResNe(X)t RoI head.

Stage of 3D ResNet. It expects to have one or more tensors as input for single pathway (C2D, I3D, Slow), and multi-pathway (SlowFast) cas

SlowFast model builder for SlowFast network. Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. "SlowFast networks for

Cross entropy loss with soft target.

Enum class for sort order. Attributes: ascend: ascend order. descend: descend order.

The standard BN layer computes stats across all examples in a GPU. In some cases it is desirable to compute stats across only a subset of exa

Swish activation function: x * sigmoid(x).

TF-example proto feature names for object detection. Holds the standard feature names to load from an Example proto for object detection. Attr

BasicHead. No pool.

Box classification head in TAPIR.

Video 3D stem module. Provides stem operations of Conv, BN, ReLU, MaxPool on input data tensor for one or multiple pathways.

Swin Transformer backbone. A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` - https:/

A class to evaluate detections using weighted PASCAL metrics. Weighted PASCAL metrics computes the mean average precision as the average precisio

A class to evaluate instance masks using weighted PASCAL metrics. Weighted PASCAL metrics computes the mean average precision as the average prec

X3D's 3D stem module. Performs a spatial followed by a depthwise temporal Convolution, BN, and Relu following by a spatiotemporal poo

X3D transformation: 1x1x1, Tx3x3 (channelwise, num_groups=dim_in), 1x1x1, augmented with (optional) SE (squeeze-excitation) on the 3x3x3